#!/bin/sh

cd "$1"

start="$2"
end="$3"
for i in $(seq $start $end); do
    cd "$i"
    cat dublin_core.xml | grep -Eo "(http|https)://[a-zA-Z0-9./?=_%&;:-]*" | sort -u | while read url; do
        filename="$(cat /dev/urandom | gtr -dc 'a-zA-Z0-9_' | fold -w 32 | head -n 1)"

	echo "$url"
	if echo "$url" | grep -q -e "file\|docs"; then
		id="$(echo "$url" | sed -r 's@.*(d/)([^?&/]+).*@\2@')"
		url="https://drive.google.com/uc?export=download&id=$id"
	fi

        curl -L "$url" -o "$filename"

	ext=""
	output="$(file $filename)"
	if echo $output | grep -q PDF; then
		ext="pdf"
		mv $filename $filename.pdf
	fi
	if echo $output | grep -q Word; then
		soffice --headless --convert-to pdf $filename;
		mv $filename $filename.docx;
		ext="word"
	fi

	if [ "$ext" = 'pdf' ] || [ "$ext" = 'docx' ]; then
		printf "$filename.pdf" | tee -a contents
		[ $ext = 'docx' ] && printf "$filename.docx" | tee -a contents
	fi
    done
    cd ..
done